I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
,
p
p
.
322
~
328
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
1
.
p
p
3
2
2
-
3
2
8
322
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Sing
le hidden
lay
er f
ee
dforwa
rd
ne
ura
l net
wo
rks
f
o
r
indoo
r air
qua
lity predic
tion
Dwi
M
a
r
is
a
M
id
y
a
n
t
i
1
,
S
y
a
m
s
ul
B
a
hri
1
,
I
lh
a
m
s
y
a
h
2
,
Z
a
l
ik
h
a
h
K
h
a
i
runn
is
a
3
,
H
a
f
izh
a
h In
s
a
ni M
id
y
a
n
t
i
4
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
m
a
t
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
s
i
t
a
s T
a
n
j
u
n
g
p
u
r
a
,
P
o
n
t
i
a
n
a
k
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
y
s
t
e
ms
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
ma
t
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
si
t
a
s T
a
n
j
u
n
g
p
u
r
a
,
P
o
n
t
i
a
n
a
k
,
I
n
d
o
n
e
s
i
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s T
a
n
j
u
n
g
p
u
r
a
,
P
o
n
t
i
a
n
a
k
,
I
n
d
o
n
e
si
a
4
M
u
si
c
S
t
u
d
y
P
r
o
g
r
a
m,
F
a
c
u
l
t
y
o
f
A
r
t
a
n
d
D
e
si
g
n
E
d
u
c
a
t
i
o
n
,
U
n
i
v
e
r
s
i
t
a
s P
e
n
d
i
d
i
k
a
n
I
n
d
o
n
e
s
i
a
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
8
,
2
0
2
4
R
ev
is
ed
No
v
7
,
2
0
2
5
Acc
ep
ted
Dec
1
5
,
2
0
2
5
In
d
o
o
r
a
ir
q
u
a
li
t
y
(IAQ
)
h
a
s
b
e
c
o
m
e
a
p
ro
b
lem
b
e
c
a
u
se
it
a
ffe
c
ts
h
u
m
a
n
h
e
a
lt
h
,
c
o
m
fo
rt,
a
n
d
p
r
o
d
u
c
ti
v
it
y
.
P
re
d
ictin
g
a
ir
q
u
a
li
ty
is
a
c
o
m
p
lex
tas
k
d
u
e
to
th
e
d
y
n
a
m
ic
n
a
tu
re
o
f
I
AQ
v
a
riab
le
v
a
lu
e
s
sim
u
lt
a
n
e
o
u
sly
.
In
th
i
s
stu
d
y
,
t
h
e
sin
g
le
h
i
d
d
e
n
lay
e
r
fe
e
d
fo
rwa
rd
n
e
u
ra
l
n
e
tw
o
rk
s
m
o
d
e
l
is
u
se
d
,
n
a
m
e
ly
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
(RB
F
),
se
lf
-
o
r
g
a
n
izi
n
g
m
a
p
s
(S
OM)
-
RBF
,
a
n
d
e
x
trem
e
lea
rn
in
g
m
a
c
h
in
e
(EL
M
)
to
c
las
sify
IAQ
.
Th
is
st
u
d
y
a
lso
o
b
se
rv
e
d
th
e
e
ffe
c
t
o
f
t
h
e
n
u
m
b
e
r
o
f
n
e
u
ro
n
s
i
n
t
h
e
h
id
d
e
n
lay
e
r
o
n
t
h
e
m
o
d
e
l
accu
ra
c
y
a
n
d
o
v
e
rfit
ti
n
g
o
f
e
a
c
h
n
e
two
r
k
.
Th
e
e
x
p
e
rime
n
tal
re
su
lt
s
sh
o
w
th
a
t
th
e
n
u
m
b
e
r
o
f
n
e
u
ro
n
s
in
t
h
e
h
id
d
e
n
lay
e
r
c
a
n
a
ffe
c
t
th
e
a
c
c
u
r
a
c
y
o
f
th
e
RBF
a
n
d
S
OM
-
RB
F
m
o
d
e
ls.
A
m
o
n
g
t
h
e
th
re
e
m
o
d
e
ls
u
se
d
,
RB
F
p
ro
d
u
c
e
s
v
e
ry
g
o
o
d
train
i
n
g
d
a
ta
a
c
c
u
ra
c
y
b
u
t
a
lso
th
e
m
o
st
sig
n
ifi
c
a
n
t
o
v
e
rfit
ti
n
g
v
a
lu
e
.
Th
e
larg
e
st
o
v
e
ra
ll
a
c
c
u
ra
c
y
wa
s
o
b
tain
e
d
u
si
n
g
S
OM
-
RB
F
,
with
a
v
a
lu
e
o
f
8
6
.
3
7
%
.
K
ey
w
o
r
d
s
:
E
x
tr
em
e
lear
n
in
g
m
ac
h
in
e
Feed
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
s
I
n
d
o
o
r
air
q
u
ality
R
ad
ial
b
asis
f
u
n
ctio
n
Self
-
o
r
g
an
izin
g
m
ap
s
Sin
g
le
h
id
d
en
lay
er
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Dwi
Ma
r
is
a
Mid
y
an
ti
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
Ma
th
e
m
atics a
n
d
Natu
r
al
Scien
ce
s
Un
iv
er
s
itas
T
an
ju
n
g
p
u
r
a
St.
Pro
f
.
Dr
.
H.
Had
a
r
i N
awa
wi,
Po
n
tian
ak
,
I
n
d
o
n
esia
E
m
ail:
d
wi.
m
ar
is
a@
s
i
s
k
o
m
.
u
n
tan
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
o
o
r
air
p
o
llu
tio
n
is
a
p
r
ess
in
g
is
s
u
e
an
d
s
er
io
u
s
ly
th
r
ea
ten
s
th
e
h
ea
lth
o
f
in
d
o
o
r
w
o
r
k
er
s
an
d
o
cc
u
p
an
ts
[
1
]
.
I
n
d
o
o
r
air
q
u
ality
(
I
AQ)
is
am
o
n
g
th
e
to
p
f
iv
e
en
v
ir
o
n
m
e
n
tal
r
is
k
s
t
o
g
lo
b
al
h
ea
lth
an
d
well
-
b
ein
g
[
2
]
.
I
AQ
h
as
b
ec
o
m
e
a
wid
ely
r
ec
o
g
n
ized
is
s
u
e,
d
r
awin
g
th
e
atten
tio
n
o
f
r
ese
ar
ch
er
s
an
d
citizen
s
to
im
p
r
o
v
e
air
q
u
ality
in
s
ch
o
o
ls
an
d
o
th
er
ed
u
ca
tio
n
al
f
a
cilities
.
A
ir
q
u
ality
ca
n
b
e
ass
ess
ed
b
ased
o
n
it
s
im
p
ac
t
o
n
h
ea
lth
,
co
m
f
o
r
t,
a
n
d
p
r
o
d
u
ctiv
ity
.
Air
q
u
ality
is
ess
en
tial
f
o
r
im
p
r
o
v
in
g
lear
n
in
g
a
b
ilit
y
an
d
ac
h
iev
em
en
t
[
3
]
.
Pre
d
ictin
g
ai
r
q
u
ality
is
co
m
p
lex
d
u
e
t
o
th
e
d
y
n
am
ic
n
at
u
r
e,
v
o
latilit
y
,
a
n
d
h
i
g
h
v
ar
iab
ilit
y
in
s
p
ac
e
a
n
d
tim
e
o
f
p
o
llu
tan
t
s
an
d
p
ar
ticu
lates
[
4
]
.
Am
o
n
g
th
e
p
o
llu
tan
ts
t
h
at
p
o
s
e
a
s
ev
er
e
th
r
ea
t
is
PM
10
.
PM
10
h
as
b
ee
n
clo
s
ely
a
s
s
o
cia
ted
with
ad
v
er
s
e
h
ea
lth
im
p
ac
ts
s
u
ch
as
r
esp
ir
ato
r
y
an
d
ca
r
d
io
v
ascu
lar
d
is
ea
s
es
[
5
]
.
I
n
th
e
g
u
id
elin
es
f
o
r
in
d
o
o
r
air
s
an
itatio
n
o
f
h
o
m
es
is
s
u
ed
b
y
th
e
R
eg
u
latio
n
o
f
th
e
M
in
is
tr
y
o
f
Hea
lth
o
f
th
e
R
ep
u
b
lic
o
f
I
n
d
o
n
esia,
th
e
I
AQ
lev
el
f
o
r
PM
10
is
≤
7
0
µg
/m
3
i
n
2
4
h
o
u
r
s
[
6
]
.
I
t
is
k
n
o
wn
t
h
at
PM
10
co
n
ce
n
tr
atio
n
s
ca
n
f
lu
ctu
ate
s
i
g
n
if
ican
tly
with
an
o
m
alies d
et
ec
ted
in
th
e
s
tu
d
y
ar
ea
[
7
]
.
I
AQ
d
eter
m
in
e
d
b
y
th
e
co
n
c
en
tr
atio
n
o
f
i
n
d
o
o
r
air
p
o
llu
tan
ts
,
ca
n
b
e
p
r
ed
icted
u
s
in
g
p
h
y
s
ically
b
ased
m
ec
h
an
is
tic
m
o
d
els
o
r
s
tatis
tical
m
o
d
els
b
ased
o
n
m
ea
s
u
r
ed
d
ata
[
8
]
.
Ar
tific
ial
n
eu
r
a
l
n
etwo
r
k
s
(
ANN)
ar
e
o
n
e
o
f
th
e
s
tatis
tical
m
et
h
o
d
s
th
at
ca
n
b
e
ap
p
lied
to
I
AQ
p
r
ed
ictio
n
.
ANN
is
an
ar
tific
ial
in
tellig
en
ce
m
o
d
el
th
at
tr
ies
to
im
itate
h
o
w
th
e
h
u
m
an
b
r
ain
wo
r
k
s
an
d
is
b
etter
at
m
an
ag
in
g
c
o
m
p
le
x
ity
an
d
u
n
ce
r
tain
ty
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
S
in
g
le
h
id
d
en
la
ye
r
feed
fo
r
w
a
r
d
n
eu
r
a
l n
etw
o
r
ks fo
r
in
d
o
o
r
a
ir
q
u
a
lity p
r
ed
ictio
n
(
Dw
i Ma
r
is
a
Mid
ya
n
ti
)
323
th
an
tr
ad
itio
n
al
m
eth
o
d
s
[
9
]
.
ANN
is
u
s
ed
f
o
r
I
AQ
p
r
ed
ict
io
n
b
ased
o
n
PM
10
v
alu
es,
in
clu
d
in
g
r
ad
ial
b
asis
f
u
n
ctio
n
n
eu
r
al
n
etwo
r
k
(
R
B
F
NN
)
[
1
0
]
.
B
r
o
o
m
h
ea
d
a
n
d
L
o
we
[
1
1
]
i
n
tr
o
d
u
ce
d
th
e
R
B
FNN
in
m
u
ltiv
ar
iab
le
f
u
n
ctio
n
al
in
ter
p
o
latio
n
an
d
ad
ap
tiv
e
n
etwo
r
k
s
.
R
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F
)
h
as
g
o
o
d
ac
cu
r
ac
y
with
a
lim
ited
n
u
m
b
er
o
f
s
en
s
o
r
s
[
1
2
]
.
I
n
s
ev
er
al
ca
s
es,
R
B
F
h
as
g
o
o
d
ac
cu
r
ac
y
[
1
3
]
–
[
1
5
]
an
d
ca
n
esti
m
ate
n
o
n
lin
ea
r
f
u
n
ctio
n
s
[
1
6
]
.
A
clu
s
ter
in
g
m
eth
o
d
ca
n
b
e
u
s
ed
to
d
eter
m
in
e
th
e
ce
n
ter
v
alu
e
in
R
B
F,
o
n
e
o
f
wh
ich
is
s
elf
-
o
r
g
a
n
izin
g
m
ap
s
(
SOM)
.
I
n
cr
em
en
tal
lea
r
n
in
g
o
f
a
s
i
n
g
le
SOM
with
R
B
F
p
er
f
o
r
m
s
b
etter
g
en
e
r
aliza
tio
n
th
a
n
tr
ad
itio
n
al
R
B
F
n
etwo
r
k
s
[
1
7
]
.
I
n
te
g
r
atin
g
th
e
SOM
clu
s
ter
in
g
alg
o
r
ith
m
a
n
d
R
B
F
NN
is
s
u
g
g
ested
to
m
ak
e
th
e
n
etwo
r
k
m
o
r
e
ef
f
ec
tiv
e
an
d
ef
f
icien
t
[
1
8
]
.
R
B
FNN
is
o
n
e
o
f
t
h
e
s
in
g
le
h
id
d
en
lay
er
f
ee
d
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
s
(
SLFNs)
m
eth
o
d
s
.
An
o
th
er
SLFNs
m
eth
o
d
is
ex
tr
em
e
l
ea
r
n
in
g
m
ac
h
in
e
(
E
L
M)
.
E
L
M
was
d
ev
elo
p
ed
b
y
Hu
an
g
et
a
l.
[
1
9
]
as
an
alg
o
r
ith
m
th
at
p
r
o
v
i
d
es
g
o
o
d
g
en
er
aliza
tio
n
p
er
f
o
r
m
an
ce
at
v
er
y
f
ast
lear
n
i
n
g
r
ates
.
T
h
e
u
s
e
o
f
E
L
M
p
r
o
d
u
ce
s
h
ig
h
ac
c
u
r
ac
y
[
2
0
]
,
i
ts
s
im
p
le
s
tr
u
ctu
r
e,
n
o
p
ar
a
m
e
ter
ad
ap
tatio
n
,
s
h
o
r
ter
p
r
o
ce
s
s
in
g
tim
e,
an
d
lo
wer
co
m
p
u
tatio
n
al
c
o
m
p
lex
ity
[
2
1
]
,
r
ed
u
cin
g
tr
ain
i
n
g
tim
e
c
o
s
ts
b
ec
au
s
e
it
d
o
es
n
o
t
h
av
e
iter
ativ
e
tu
n
in
g
p
ar
am
eter
s
as a
s
u
b
s
titu
te
f
o
r
t
r
ad
itio
n
al
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
[
2
2
]
.
T
h
e
m
ain
o
b
jectiv
e
o
f
th
is
p
ap
er
is
to
p
r
o
p
o
s
e
R
B
F,
SOM
-
R
B
F,
an
d
E
L
M
m
o
d
els
to
p
r
e
d
ict
I
AQ.
R
B
F,
SOM
-
R
B
F,
an
d
E
L
M
m
o
d
els
will
b
e
in
v
esti
g
ated
t
o
d
eter
m
in
e
I
AQ
b
ased
o
n
te
m
p
er
atu
r
e,
h
u
m
i
d
ity
,
an
d
PM
10
in
p
u
ts
.
T
h
e
f
o
llo
wi
n
g
s
ec
tio
n
will
p
r
esen
t
th
e
alg
o
r
ith
m
s
u
s
ed
in
th
is
r
esear
ch
.
Sectio
n
2
d
escr
ib
es
th
e
p
r
o
p
o
s
ed
m
o
d
el
an
d
d
ataset.
E
x
p
er
im
en
tal
r
esu
lts
ar
e
co
v
er
ed
in
s
ec
tio
n
3
.
Fin
ally
,
th
e
co
n
clu
s
io
n
an
d
f
u
tu
r
e
wo
r
k
o
f
th
is
p
ap
er
ar
e
m
en
tio
n
ed
i
n
s
ec
tio
n
4
.
2.
M
E
T
H
O
D
T
h
e
s
u
g
g
ested
m
eth
o
d
s
tep
s
ar
e
in
clu
d
ed
in
th
is
s
ec
tio
n
.
T
h
e
s
u
g
g
ested
p
r
o
ce
d
u
r
e
s
tar
ts
with
r
eq
u
ir
em
e
n
ts
an
aly
s
is
,
d
ata
a
cq
u
is
itio
n
,
d
ata
co
llectio
n
,
d
ata
lab
elin
g
,
b
u
ild
in
g
th
e
ANN
m
o
d
el,
test
in
g
m
o
d
el,
an
d
p
er
f
o
r
m
a
n
ce
an
aly
s
is
.
Fig
u
r
e
1
s
h
o
ws th
e
wo
r
k
in
g
p
r
o
ce
s
s
o
f
t
h
is
s
tu
d
y
.
Fig
u
r
e
1
.
Ov
e
r
all
wo
r
k
in
g
p
r
o
ce
s
s
2
.
1
.
Requirem
ent
a
na
ly
s
is
At
th
is
s
tag
e,
f
u
n
ctio
n
al
an
d
n
o
n
-
f
u
n
ctio
n
al
n
ee
d
s
an
aly
s
is
i
s
ca
r
r
ied
o
u
t.
Fo
r
f
u
n
ctio
n
al
n
ee
d
s
,
I
AQ
p
ar
am
eter
s
s
u
ch
as
PM
10
,
te
m
p
er
atu
r
e,
an
d
h
u
m
id
ity
ar
e
n
ee
d
ed
,
an
d
th
e
r
o
o
m
will
u
s
ed
as
th
e
o
b
ject
o
f
r
esear
ch
.
DHT
2
2
s
en
s
o
r
is
u
s
ed
to
m
ea
s
u
r
e
tem
p
er
at
u
r
e
a
n
d
h
u
m
i
d
ity
,
E
SP
3
2
is
u
s
ed
as
a
m
icr
o
c
o
n
tr
o
ller
m
o
d
u
le,
an
d
th
e
d
u
s
t
s
en
s
o
r
is
u
s
ed
as
a
PM
10
co
u
n
ter
.
T
h
e
f
ee
d
f
o
r
war
d
ANN
m
o
d
el
u
s
ed
in
th
is
s
tu
d
y
f
o
r
non
-
f
u
n
ctio
n
al
n
ee
d
s
is
R
B
F,
SOM
-
R
B
F,
an
d
E
L
M.
2
.
2
.
Da
t
a
a
cquis
it
io
n
At
th
is
s
tag
e,
d
ata
g
en
e
r
ated
b
y
th
e
DHT
2
2
s
en
s
o
r
an
d
th
e
GP2
Y1
0
1
0
AU0
F
d
u
s
t
s
en
s
o
r
co
n
n
ec
ted
to
th
e
E
SP
3
2
m
icr
o
c
o
n
tr
o
ller
is
s
en
t
to
th
e
s
er
v
er
.
Fro
m
th
e
s
er
v
er
,
th
e
d
ata
is
d
is
p
lay
ed
o
n
th
e
web
s
ite.
T
h
is
d
ata
tr
an
s
m
is
s
io
n
d
ep
en
d
s
o
n
th
e
W
i
-
F
i
co
n
n
ec
tiv
ity
in
th
e
v
icin
ity
o
f
th
e
E
SP
3
2
m
ic
r
o
co
n
tr
o
ller
.
Af
ter
th
e
d
ata
is
co
llected
,
d
ata
clea
n
in
g
an
d
f
ilter
in
g
ar
e
p
e
r
f
o
r
m
ed
to
p
r
e
p
ar
e
th
e
d
ata
f
o
r
u
s
e
i
n
th
e
n
e
x
t stag
e.
2
.
3
.
Da
t
a
la
belin
g
I
n
th
is
s
tu
d
y
,
th
e
in
p
u
ts
u
s
ed
ar
e
tem
p
er
atu
r
e,
h
u
m
id
ity
,
an
d
PM
10
.
T
h
e
o
u
tp
u
t
u
s
ed
is
th
e
p
r
ed
ictio
n
o
f
PM
10
ca
teg
o
r
ies
f
o
r
th
e
n
ex
t
2
4
h
o
u
r
s
.
B
ased
o
n
th
e
g
u
id
elin
es
f
o
r
in
d
o
o
r
air
s
an
itatio
n
is
s
u
ed
b
y
th
e
Min
is
tr
y
o
f
Hea
lth
o
f
th
e
R
ep
u
b
lic
o
f
I
n
d
o
n
esia,
th
e
r
eq
u
ir
e
d
lev
el
f
o
r
PM
10
is
≤
7
0
in
2
4
h
o
u
r
s
.
T
h
er
e
f
o
r
e,
w
e
cr
ea
ted
two
p
r
ed
ictio
n
class
es:
if
th
e
PM
10
v
alu
e
≤
7
0
,
th
en
th
e
class
i
s
n
o
t
d
an
g
er
o
u
s
,
an
d
if
PM
10
≥
7
0
,
th
e
class
is
d
an
g
er
o
u
s
.
2
.
4
.
Art
if
ici
a
l neura
l net
wo
rk
s
m
o
del
ANN
ar
e
an
in
f
o
r
m
ati
o
n
p
r
o
c
ess
in
g
p
ar
ad
ig
m
in
s
p
ir
e
d
b
y
h
o
w
b
io
lo
g
ical
n
e
r
v
o
u
s
s
y
s
tem
s
,
s
u
ch
as
th
e
b
r
ain
,
p
r
o
ce
s
s
in
f
o
r
m
atio
n
[
2
3
]
.
T
h
e
n
u
m
b
e
r
o
f
n
eu
r
o
n
s
in
th
e
h
id
d
en
lay
er
,
lear
n
in
g
r
ate,
n
etwo
r
k
weig
h
ts
,
th
r
esh
o
ld
,
an
d
ac
tiv
a
tio
n
f
u
n
ctio
n
ar
e
s
o
m
e
o
f
th
e
p
ar
am
eter
s
th
at
ca
n
af
f
ec
t
th
e
o
u
tp
u
t
v
alu
e
o
f
th
e
n
etwo
r
k
.
Sp
ec
if
ically
,
f
o
r
d
at
a
s
ets
w
ith
s
am
p
le
s
ize
s
u
n
d
er
1
0
,
0
0
0
,
th
e
to
tal
n
u
m
b
er
o
f
h
id
d
en
n
e
u
r
o
n
s
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
322
-
3
2
8
324
s
elec
ted
f
r
o
m
{1
0
,
1
5
,
2
0
,
…,
5
4
0
,
5
4
5
,
5
5
0
};
f
o
r
d
ata
s
ets
with
s
am
p
le
s
izes
ab
o
v
e
1
0
,
0
0
0
,
th
e
to
tal
n
u
m
b
e
r
o
f
h
id
d
e
n
n
eu
r
o
n
s
is
s
elec
ted
f
r
o
m
{5
0
,
6
0
,
7
0
,
…,
8
8
0
,
8
9
0
,
9
0
0
}
[
2
4
]
.
Go
n
i
et
a
l.
[
2
1
]
u
s
ed
a
h
id
d
en
lay
er
o
f
th
e
E
L
M
m
o
d
el
with
7
0
0
n
eu
r
o
n
s
.
Netwo
r
k
weig
h
ts
ca
n
b
e
ch
o
s
en
r
an
d
o
m
l
y
.
Neu
r
al
n
etwo
r
k
s
with
r
an
d
o
m
weig
h
ts
(
NNRW
)
h
av
e
s
ig
n
if
ican
t
tr
ain
in
g
tim
e
r
e
d
u
c
tio
n
wh
ile
m
ain
tain
in
g
h
ig
h
p
r
ed
ictio
n
ac
cu
r
ac
y
[
2
5
]
,
ef
f
ec
ti
v
en
ess
in
h
an
d
lin
g
co
n
ce
p
t
s
h
if
ts
[
2
6
]
,
a
n
d
th
e
u
s
e
o
f
NNRW
in
E
L
M
ca
n
p
r
o
d
u
ce
h
ig
h
ac
cu
r
ac
y
r
ates
[
2
7
]
.
T
h
is
s
tu
d
y
u
s
es
th
r
ee
m
o
d
els,
n
am
el
y
R
B
F,
SOM
-
R
B
F,
an
d
E
L
M.
T
h
e
n
etwo
r
k
m
o
d
el
is
a
SLFNs
n
etwo
r
k
m
o
d
el.
T
h
e
n
etwo
r
k
ar
ch
itectu
r
e
ca
n
b
e
s
ee
n
in
Fig
u
r
e
2
.
T
h
is
s
tu
d
y
u
s
es
th
r
ee
in
p
u
t
n
o
d
es:
tem
p
er
at
u
r
e,
h
u
m
i
d
ity
,
an
d
PM
10
,
o
n
e
h
id
d
en
la
y
e
r
,
an
d
two
o
u
tp
u
t
n
o
d
es.
No
r
m
aliza
tio
n
i
n
R
B
F
an
d
SOM
u
s
es
m
in
-
m
ax
n
o
r
m
aliza
tio
n
[
2
8
]
–
[
3
1
]
with
a
r
a
n
g
e
o
f
[
0
,
1
]
.
Fo
r
th
e
E
L
M
m
o
d
el,
we
u
s
e
m
in
-
m
ax
n
o
r
m
aliza
tio
n
with
a
r
an
g
e
o
f
[
-
1
1
]
,
as
d
o
n
e
in
th
e
s
tu
d
ies
[
3
2
]
,
[
3
3
]
.
T
h
e
f
o
r
m
u
la
f
o
r
m
in
-
m
ax
n
o
r
m
aliza
tio
n
is
as
s
h
o
wn
in
(
1
)
[
2
8
]
.
=
−
−
(
1
)
T
h
e
So
f
tMa
x
ac
tiv
atio
n
f
u
n
cti
o
n
is
ap
p
lied
to
th
e
o
u
tp
u
t
v
al
u
e.
T
h
is
f
u
n
ctio
n
m
ak
es
it
ea
s
ier
to
d
eter
m
in
e
th
e
class
o
f
th
e
o
u
tp
u
t
v
alu
e.
T
h
e
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
is
d
ef
in
ed
as
(
2
)
a
n
d
(
3
)
[
3
4
]
.
̂
=
(
ℎ
(
)
)
(
2
)
(
ℎ
,
)
=
ex
p
(
ℎ
,
)
∑
ex
p
(
ℎ
,
)
(
3
)
W
h
e
r
e
ℎ
,
i
s
a
s
c
al
a
r
v
a
l
u
e
f
o
r
e
a
c
h
c
l
a
s
s
c
i
n
t
h
e
o
u
t
p
u
t
v
e
c
t
o
r
h
v
o
f
t
h
e
l
a
s
t
l
a
y
e
r
,
a
n
d
t
h
e
S
o
f
t
M
a
x
a
c
t
i
v
a
ti
o
n
f
u
n
c
t
i
o
n
i
s
c
o
m
p
u
t
e
d
f
o
r
e
a
c
h
c
l
a
s
s
.
M
o
d
e
l
te
s
ti
n
g
i
s
c
o
n
d
u
c
te
d
a
f
t
e
r
t
h
e
o
p
t
i
m
a
l
AN
N
m
o
d
e
l
h
a
s
b
e
e
n
d
e
r
i
v
e
d
f
r
o
m
t
h
e
t
r
a
i
n
i
n
g
d
a
ta
.
T
r
a
i
n
i
n
g
d
a
t
a
is
u
s
e
d
a
s
m
u
c
h
a
s
7
0
%
o
f
t
h
e
t
o
t
al
d
a
t
a
,
a
n
d
t
es
t
d
a
ta
i
s
u
s
e
d
as
m
u
c
h
as
3
0
%
.
P
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
s
is
is
co
n
d
u
c
t
e
d
t
o
a
s
s
e
s
s
t
h
e
e
f
f
i
c
a
c
y
o
f
t
h
e
A
N
N
m
o
d
el
.
M
e
a
n
s
q
u
a
r
e
d
e
r
r
o
r
(
M
S
E
)
is
u
s
e
d
t
o
d
e
t
e
r
m
i
n
e
t
h
e
e
r
r
o
r
o
f
t
r
a
i
n
i
n
g
d
a
t
a
s
o
t
h
a
t
t
h
e
b
e
s
t
m
o
d
e
l
f
r
o
m
t
r
a
i
n
i
n
g
d
a
t
a
c
a
n
b
e
s
e
l
e
ct
e
d
f
o
r
t
e
s
t
i
n
g
t
e
s
t
d
at
a
.
C
o
n
f
u
s
i
o
n
m
a
t
r
i
x
is
u
s
e
d
t
o
d
e
t
e
r
m
i
n
e
t
h
e
o
v
e
r
a
l
l
p
er
f
o
r
m
a
n
c
e
a
n
a
l
y
s
is
a
s
i
n
t
h
e
s
t
u
d
y
[
3
5
]
.
Fig
u
r
e
2
.
Neu
r
al
n
etwo
r
k
ar
ch
itectu
r
e
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Resul
t
o
f
a
rt
if
icia
l neura
l net
wo
rk
T
h
is
s
tu
d
y
u
s
ed
9
1
0
d
ata,
d
iv
id
ed
in
to
6
3
7
d
ata
f
o
r
tr
ai
n
in
g
d
ata
an
d
2
7
3
f
o
r
test
d
ata.
T
h
e
p
ar
am
eter
s
u
s
ed
ar
e
t
h
e
n
u
m
b
er
o
f
i
n
p
u
t
n
eu
r
o
n
s
o
f
3
n
eu
r
o
n
s
,
o
n
e
h
id
d
en
la
y
e
r
,
an
d
o
n
e
o
u
tp
u
t.
Ob
s
er
v
atio
n
s
wer
e
m
ad
e
o
n
t
h
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
in
th
e
h
i
d
d
en
lay
er
f
r
o
m
5
0
-
7
0
0
n
eu
r
o
n
s
with
m
u
ltip
les o
f
5
0
{
5
0
,
1
0
0
,
1
5
0
,
.
.
.
,
7
0
0
}.
W
e
also
co
n
s
id
er
ed
th
e
o
v
er
f
itti
n
g
v
alu
e
o
f
th
e
tr
ain
in
g
m
o
d
el
o
b
tain
e
d
a
g
ain
s
t
th
e
test
d
ata.
E
ac
h
tim
e
th
e
n
etwo
r
k
was
tr
ain
ed
with
a
ce
r
tain
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
1
h
id
d
en
lay
er
,
4
0
tr
ials
wer
e
ca
r
r
ied
o
u
t
to
g
et
th
e
b
e
s
t
weig
h
t
an
d
b
ias
v
alu
es
f
r
o
m
ea
ch
m
o
d
el
th
at
p
r
o
d
u
ce
d
t
h
e
h
ig
h
est
ac
cu
r
ac
y
.
Fro
m
th
e
4
0
tr
ials
,
1
d
ata
with
th
e
h
ig
h
est
ac
c
u
r
ac
y
v
alu
e
o
r
th
e
l
o
west
MSE
was
s
elec
ted
.
T
h
e
weig
h
t
v
alu
e
o
f
th
e
tr
ain
in
g
d
ata
with
th
e
h
ig
h
est
ac
cu
r
ac
y
was
u
s
ed
to
co
n
d
u
ct
th
e
d
ata
test
.
Fig
u
r
e
3
is
th
e
r
e
s
u
lt
o
f
tr
ain
in
g
d
ata
u
s
in
g
a
d
if
f
er
en
t
n
u
m
b
er
o
f
n
e
u
r
o
n
s
.
Fig
u
r
e
3
s
h
o
ws
th
at
t
h
e
n
u
m
b
e
r
o
f
n
e
u
r
o
n
s
i
n
th
e
h
i
d
d
en
lay
er
af
f
ec
ts
th
e
MSE
v
alu
e
in
th
e
R
B
F
an
d
SOM
-
R
B
F
m
o
d
el.
I
n
t
h
e
R
B
F
an
d
SOM
-
R
B
F
m
o
d
els,
th
e
h
ig
h
er
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
1
h
id
d
en
lay
er
,
th
e
lo
wer
th
e
r
esu
ltin
g
MSE
v
alu
e.
I
n
th
e
E
L
M
m
o
d
el,
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
h
as a
lo
w
e
f
f
ec
t o
n
th
e
MSE
v
alu
e
o
f
th
e
n
etwo
r
k
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
S
in
g
le
h
id
d
en
la
ye
r
feed
fo
r
w
a
r
d
n
eu
r
a
l n
etw
o
r
ks fo
r
in
d
o
o
r
a
ir
q
u
a
lity p
r
ed
ictio
n
(
Dw
i Ma
r
is
a
Mid
ya
n
ti
)
325
W
e
o
b
s
er
v
e
th
e
o
v
e
r
f
itti
n
g
v
al
u
e
p
r
o
d
u
ce
d
b
y
ea
c
h
m
o
d
el.
Fig
u
r
e
4
s
h
o
ws
th
e
o
v
er
f
itti
n
g
m
o
d
el
th
at
R
B
F,
SOM
-
R
B
F,
an
d
E
L
M
p
r
o
d
u
ce
d
.
I
n
Fig
u
r
e
4
(
a)
,
th
e
s
m
allest
o
v
er
f
itti
n
g
is
p
r
o
d
u
ce
d
b
y
R
B
F
wh
en
u
s
in
g
2
0
0
n
eu
r
o
n
s
in
th
e
h
id
d
en
lay
er
,
with
an
ac
cu
r
ac
y
d
if
f
er
en
ce
o
f
0
.
1
2
0
8
7
9
.
I
n
Fig
u
r
e
4
(
b
)
,
th
e
lar
g
est
o
v
er
f
itti
n
g
is
p
r
o
d
u
ce
d
b
y
S
OM
-
R
B
F
wh
en
u
s
in
g
5
5
0
n
eu
r
o
n
s
in
t
h
e
h
id
d
en
lay
e
r
,
with
an
ac
cu
r
ac
y
d
if
f
er
en
ce
o
f
0
.
0
1
9
8
8
5
.
I
n
Fig
u
r
e
4
(
c)
,
th
e
lar
g
est
o
v
er
f
itti
n
g
is
p
r
o
d
u
ce
d
b
y
E
L
M
wh
e
n
u
s
in
g
6
0
0
n
eu
r
o
n
s
i
n
th
e
h
id
d
en
lay
er
,
with
an
ac
c
u
r
ac
y
d
if
f
e
r
en
ce
o
f
0
.
0
4
9
1
8
9
.
Fig
u
r
e
4
s
h
o
ws
th
at
th
e
g
r
ea
ter
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
th
e
R
B
F
h
id
d
en
la
y
er
,
th
e
g
r
ea
ter
t
h
e
o
v
e
r
f
itti
n
g
v
alu
e.
Me
an
w
h
ile,
f
o
r
th
e
SO
M
-
R
B
F
m
o
d
el,
th
e
g
r
ea
ter
th
e
n
u
m
b
e
r
o
f
n
eu
r
o
n
s
in
th
e
h
id
d
e
n
lay
er
u
s
ed
,
th
e
s
m
aller
th
e
o
v
er
f
itti
n
g
v
alu
e
p
r
o
d
u
ce
d
.
I
n
th
e
E
L
M
m
o
d
el,
ch
a
n
g
es
in
th
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
th
e
h
id
d
e
n
lay
er
d
o
n
o
t
s
ig
n
if
ican
tly
af
f
ec
t
th
e
o
v
er
f
itti
n
g
v
alu
e
cr
ea
ted
b
y
th
e
m
o
d
el.
T
h
is
ca
n
h
ap
p
en
b
ec
au
s
e
th
e
d
ata
u
s
ed
is
n
o
t
v
ar
ied
o
r
th
er
e
is
n
o
d
ata
b
alan
ce
b
etwe
en
class
es.
T
h
e
m
in
im
u
m
o
v
e
r
f
itti
n
g
o
f
th
e
R
B
F
m
o
d
el
is
o
b
tain
ed
b
y
u
s
in
g
2
0
0
n
e
u
r
o
n
s
in
th
e
h
id
d
e
n
lay
er
.
T
h
e
m
i
n
im
u
m
o
v
e
r
f
itti
n
g
o
f
t
h
e
SOM
-
R
B
F
m
o
d
el
i
s
o
b
tain
ed
b
y
u
s
in
g
5
5
0
n
eu
r
o
n
s
in
th
e
h
id
d
e
n
lay
er
.
T
h
e
m
in
im
u
m
o
v
er
f
itti
n
g
o
f
th
e
E
L
M
m
o
d
el
is
o
b
tain
e
d
b
y
u
s
in
g
6
0
0
n
e
u
r
o
n
s
in
th
e
h
id
d
en
la
y
er
.
T
ab
le
1
s
h
o
ws
th
at
t
h
e
h
ig
h
est
tr
ain
in
g
d
ata
ac
cu
r
ac
y
is
ac
h
i
ev
ed
u
s
in
g
th
e
R
B
F
m
eth
o
d
.
F
o
r
th
e
test
d
ata,
th
e
b
est
ac
cu
r
ac
y
is
o
b
tain
ed
with
th
e
SOM
-
R
B
F
m
et
h
o
d
.
Ov
er
all,
u
s
in
g
9
1
0
d
ata,
th
e
b
est
ac
cu
r
ac
y
i
s
ac
h
iev
ed
u
s
in
g
th
e
SOM
-
R
B
F
m
eth
o
d
,
with
an
o
v
er
all
ac
cu
r
ac
y
o
f
8
6
.
3
7
%.
Fig
u
r
e
3
.
T
r
ain
in
g
d
ata
r
esu
lt
(
a)
(
b
)
(
c)
Fig
u
r
e
4
.
Ov
e
r
f
itti
n
g
m
o
d
el
f
o
r
(
a)
R
B
F,
(
b
)
SOM
-
R
B
F,
an
d
(
c)
E
L
M
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
322
-
3
2
8
326
T
ab
le
1
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
M
o
d
e
l
TP
FN
TN
FP
To
t
a
l
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
S
p
e
c
i
f
i
c
i
t
y
F
1
-
s
c
o
r
e
A
c
c
u
r
a
c
y
(
%)
R
B
F
t
r
a
i
n
i
n
g
s
e
t
44
55
5
3
5
3
6
3
7
9
3
.
6
2
4
4
.
4
4
0
.
9
9
6
0
.
2
7
9
0
.
8
9
R
B
F
t
e
s
t
i
n
g
se
t
19
23
1
8
7
44
2
7
3
3
0
.
1
6
4
5
.
2
4
0
.
8
1
3
6
.
1
9
7
5
.
4
6
O
v
e
r
a
l
l
63
78
7
2
2
47
9
1
0
5
7
.
2
7
4
4
.
6
8
0
.
9
4
5
0
.
2
0
8
6
.
2
6
S
O
M
-
R
B
F
t
r
a
i
n
i
n
g
set
18
81
5
3
8
0
6
3
7
1
0
0
1
8
.
1
8
1
3
0
.
7
7
8
7
.
2
8
S
O
M
-
R
B
F
t
e
st
i
n
g
s
e
t
2
40
2
2
8
3
2
7
3
40
4
.
7
6
0
.
9
9
8
.
5
1
8
4
.
2
5
O
v
e
r
a
l
l
20
1
2
1
7
6
6
3
9
1
0
8
6
.
9
6
1
4
.
1
8
1
2
4
.
3
9
8
6
.
3
7
ELM
t
r
a
i
n
i
n
g
set
9
90
5
3
7
1
6
3
7
90
9
.
0
9
1
1
6
.
5
1
8
5
.
7
1
ELM
t
e
st
i
n
g
s
e
t
1
41
2
2
4
7
2
7
3
1
2
.
5
0
2
.
3
8
0
.
9
7
4
8
2
.
4
2
O
v
e
r
a
l
l
10
1
3
1
7
6
1
8
9
1
0
5
5
.
5
6
7
.
0
9
0
.
9
9
1
2
.
5
8
8
4
.
7
3
4.
CO
NCLU
SI
O
N
I
AQ
h
as
b
ec
o
m
e
a
p
r
o
b
l
em
b
e
ca
u
s
e
it
af
f
e
cts
h
e
alt
h
,
c
o
m
f
o
r
t
,
a
n
d
p
r
o
d
u
ct
iv
it
y
.
Pr
ed
ict
in
g
air
q
u
alit
y
is
a
co
m
p
le
x
tas
k
d
u
e
to
t
h
e
d
y
n
am
ic
n
a
tu
r
e
o
f
I
A
Q
v
a
r
ia
b
le
v
al
u
es
s
im
u
l
ta
n
e
o
u
s
l
y
.
R
B
F,
SOM
-
R
B
F,
a
n
d
E
L
M
a
r
e
p
r
o
p
o
s
e
d
to
h
el
p
p
r
ed
i
ct
I
AQ.
T
h
e
I
AQ
v
a
r
i
ab
les
u
s
ed
ar
e
t
em
p
er
at
u
r
e,
h
u
m
i
d
i
ty
,
an
d
PM
10
.
T
h
e
n
u
m
b
e
r
o
f
n
e
u
r
o
n
s
i
n
o
n
e
h
i
d
d
e
n
l
ay
er
an
d
o
v
e
r
f
itti
n
g
i
n
t
h
is
s
t
u
d
y
a
r
e
a
ls
o
c
o
n
s
id
er
e
d
.
T
h
e
e
x
p
e
r
im
e
n
t
was
co
n
d
u
ct
ed
4
0
t
im
es
u
s
i
n
g
r
a
n
d
o
m
v
al
u
es
f
o
r
e
ac
h
n
u
m
b
er
o
f
n
e
u
r
o
n
s
to
o
b
tai
n
t
h
e
s
m
all
est
MS
E
v
a
lu
e
o
n
th
e
tr
a
in
in
g
d
at
a.
T
h
e
r
es
u
l
ts
o
f
t
h
e
e
x
p
e
r
i
m
e
n
t
s
h
o
w
t
h
at
R
B
F
h
as
a
h
ig
h
er
F
1
-
s
c
o
r
e
v
a
lu
e
t
h
a
n
SOM
-
R
B
F
an
d
E
L
M
.
R
B
F
h
as
t
h
e
la
r
g
est
ac
c
u
r
ac
y
o
n
t
r
ai
n
i
n
g
d
at
a
b
u
t
h
as
lar
g
e
o
v
er
f
it
ti
n
g
wh
e
n
c
o
m
p
ar
ed
t
o
o
t
h
e
r
m
o
d
els
.
Ov
e
r
a
ll
,
SO
M
-
R
B
F
h
as
t
h
e
h
i
g
h
est
a
cc
u
r
ac
y
o
f
8
6
.
3
7
%
,
R
B
F a
t
8
6
.
2
6
%
,
a
n
d
E
L
M
a
t
8
4
.
7
3
%.
ACK
NO
WL
E
DG
M
E
N
T
S
Au
th
o
r
th
a
n
k
s
to
th
e
Facu
lt
y
o
f
Ma
th
em
atics
an
d
Natu
r
al
Scien
ce
s
,
T
an
ju
n
g
p
u
r
a
Un
iv
er
s
ity
,
Po
n
tian
ak
,
I
n
d
o
n
esia,
f
o
r
s
u
p
p
o
r
tin
g
th
is
r
esear
ch
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Dwi
Ma
r
is
a
Mid
y
an
ti
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sy
am
s
u
l Bah
r
i
✓
✓
✓
✓
✓
✓
✓
✓
I
lh
am
s
y
ah
✓
✓
✓
Z
alik
h
ah
Kh
air
u
n
n
is
a
✓
✓
✓
✓
H
a
f
i
z
h
a
h
I
n
s
a
n
i
M
i
d
y
a
n
t
i
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
DATA AV
AI
L
AB
I
L
I
T
Y
Der
iv
ed
d
ata
s
u
p
p
o
r
tin
g
t
h
e
f
in
d
in
g
s
o
f
t
h
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
i
n
g
au
th
o
r
,
[
DM
M]
,
o
n
r
eq
u
est.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
S
in
g
le
h
id
d
en
la
ye
r
feed
fo
r
w
a
r
d
n
eu
r
a
l n
etw
o
r
ks fo
r
in
d
o
o
r
a
ir
q
u
a
lity p
r
ed
ictio
n
(
Dw
i Ma
r
is
a
Mid
ya
n
ti
)
327
RE
F
E
R
E
NC
E
S
[
1
]
H
.
L
o
n
g
e
t
a
l
.
,
“
R
e
v
e
a
l
i
n
g
l
o
n
g
-
t
e
r
m
i
n
d
o
o
r
a
i
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
:
a
n
i
n
t
e
l
l
i
g
e
n
t
i
n
f
o
r
m
e
r
-
b
a
s
e
d
a
p
p
r
o
a
c
h
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
1
8
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
1
8
8
0
0
3
.
[
2
]
J.
S
a
i
n
i
,
M
.
D
u
t
t
a
,
a
n
d
G
.
M
a
r
q
u
e
s,
“
I
n
d
o
o
r
a
i
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
s
y
st
e
ms
f
o
r
smar
t
e
n
v
i
r
o
n
me
n
t
s:
a
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
m
a
rt
E
n
v
i
r
o
n
m
e
n
t
s
,
v
o
l
.
1
2
,
n
o
.
5
,
p
p
.
4
3
3
–
4
5
3
,
2
0
2
0
,
d
o
i
:
1
0
.
3
2
3
3
/
a
i
s
-
2
0
0
5
7
4
.
[
3
]
I
.
La
z
o
v
i
c
,
Z.
S
t
e
v
a
n
o
v
i
c
,
M
.
J
.
-
S
t
o
j
a
n
o
v
i
c
,
M
.
Z
i
v
k
o
v
i
c
,
a
n
d
M
.
B
a
n
j
a
c
,
“
I
mp
a
c
t
o
f
C
O
2
c
o
n
c
e
n
t
r
a
t
i
o
n
o
n
i
n
d
o
o
r
a
i
r
q
u
a
l
i
t
y
a
n
d
c
o
r
r
e
l
a
t
i
o
n
w
i
t
h
r
e
l
a
t
i
v
e
h
u
m
i
d
i
t
y
a
n
d
i
n
d
o
o
r
a
i
r
t
e
m
p
e
r
a
t
u
r
e
i
n
sc
h
o
o
l
b
u
i
l
d
i
n
g
s
i
n
S
e
r
b
i
a
,
”
T
h
e
rm
a
l
S
c
i
e
n
c
e
,
v
o
l
.
2
0
,
p
p
.
2
9
7
–
3
0
7
,
2
0
1
6
,
d
o
i
:
1
0
.
2
2
9
8
/
t
sci
1
5
0
8
3
1
1
7
3
l
.
[
4
]
M
.
C
a
s
t
e
l
l
i
,
F
.
M
.
C
l
e
m
e
n
t
e
,
A
.
P
o
p
o
v
i
č
,
S
.
S
i
l
v
a
,
a
n
d
L.
V
a
n
n
e
s
c
h
i
,
“
A
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
p
r
e
d
i
c
t
a
i
r
q
u
a
l
i
t
y
i
n
C
a
l
i
f
o
r
n
i
a
,
”
C
o
m
p
l
e
x
i
t
y
,
v
o
l
.
2
0
2
0
,
p
p
.
1
–
2
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
8
0
4
9
5
0
4
.
[
5
]
B.
-
J.
Le
e
,
B
.
K
i
m
,
a
n
d
K
.
Le
e
,
“
A
i
r
p
o
l
l
u
t
i
o
n
e
x
p
o
su
r
e
a
n
d
c
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
se
a
se
,
”
T
o
x
i
c
o
l
o
g
i
c
a
l
Re
s
e
a
r
c
h
,
v
o
l
.
3
0
,
n
o
.
2
,
p
p
.
7
1
–
7
5
,
2
0
1
4
,
d
o
i
:
1
0
.
5
4
8
7
/
t
r
.
2
0
1
4
.
3
0
.
2
.
0
7
1
.
[
6
]
M
i
n
i
s
t
r
y
o
f
H
e
a
l
t
h
o
f
t
h
e
R
e
p
u
b
l
i
c
o
f
I
n
d
o
n
e
s
i
a
,
G
u
i
d
e
l
i
n
e
s
f
o
r
i
n
d
o
o
r
a
i
r
q
u
a
l
i
t
y
i
n
h
o
u
s
e
h
o
l
d
s
.
P
u
b
l
i
c
l
a
w
N
o
.
1
0
7
7
/
M
EN
K
ES/P
ER
/
V
/
2
0
1
1
,
J
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
:
M
e
n
k
e
s
,
2
0
1
1
.
[
7
]
R
.
S
a
q
e
r
,
S
.
I
ssa,
a
n
d
N
.
S
a
l
e
o
u
s,
“
S
p
a
t
i
o
-
t
e
mp
o
r
a
l
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
o
f
P
M
1
0
c
o
n
c
e
n
t
r
a
t
i
o
n
a
c
r
o
ss
A
b
u
D
h
a
b
i
Emi
r
a
t
e
(
U
A
E)
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
1
2
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
3
2
8
1
2
.
[
8
]
W
.
W
e
i
,
O
.
R
a
m
a
l
h
o
,
L
.
M
a
l
i
n
g
r
e
,
S
.
S
i
v
a
n
a
n
t
h
a
m
,
J.
C
.
Li
t
t
l
e
,
a
n
d
C
.
M
a
n
d
i
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
s
t
a
t
i
st
i
c
a
l
mo
d
e
l
s
f
o
r
p
r
e
d
i
c
t
i
n
g
i
n
d
o
o
r
a
i
r
q
u
a
l
i
t
y
,
”
I
n
d
o
o
r
Ai
r
,
v
o
l
.
2
9
,
n
o
.
5
,
p
p
.
7
0
4
–
7
2
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
1
1
/
i
n
a
.
1
2
5
8
0
.
[
9
]
T.
G
e
g
o
v
s
k
a
,
R
.
K
o
k
e
r
,
a
n
d
T
.
C
a
k
a
r
,
“
G
r
e
e
n
s
u
p
p
l
i
e
r
se
l
e
c
t
i
o
n
u
s
i
n
g
f
u
z
z
y
m
u
l
t
i
p
l
e
-
c
r
i
t
e
r
i
a
d
e
c
i
si
o
n
-
ma
k
i
n
g
met
h
o
d
s
a
n
d
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
s
c
i
e
n
c
e
,
v
o
l
.
2
0
2
0
,
p
p
.
1
–
2
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
8
8
1
1
8
3
4
.
[
1
0
]
G
.
S
u
n
,
S
.
J.
H
o
f
f
,
B
.
C
.
Ze
l
l
e
,
a
n
d
M
.
A
.
N
e
l
s
o
n
,
“
F
o
r
e
c
a
s
t
i
n
g
d
a
i
l
y
s
o
u
r
c
e
a
i
r
q
u
a
l
i
t
y
u
s
i
n
g
m
u
l
t
i
v
a
r
i
a
t
e
s
t
a
t
i
st
i
c
a
l
a
n
a
l
y
si
s
a
n
d
r
a
d
i
a
l
b
a
s
i
s
f
u
n
c
t
i
o
n
n
e
t
w
o
r
k
s
,
”
J
o
u
rn
a
l
o
f
t
h
e
Ai
r
&
W
a
st
e
M
a
n
a
g
e
m
e
n
t
As
so
c
i
a
t
i
o
n
,
v
o
l
.
5
8
,
n
o
.
1
2
,
p
p
.
1
5
7
1
–
1
5
7
8
,
2
0
0
8
,
d
o
i
:
1
0
.
3
1
5
5
/
1
0
4
7
-
3
2
8
9
.
5
8
.
1
2
.
1
5
7
1
.
[
1
1
]
D
.
S
.
B
r
o
o
m
h
e
a
d
a
n
d
D
.
L
o
w
e
,
“
M
u
l
t
i
v
a
r
i
a
b
l
e
f
u
n
c
t
i
o
n
a
l
i
n
t
e
r
p
o
l
a
t
i
o
n
a
n
d
a
d
a
p
t
i
v
e
n
e
t
w
o
r
k
s,
”
C
o
m
p
l
e
x
S
y
st
e
m
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
3
2
1
–
3
5
5
,
1
9
8
8
.
[
1
2
]
J.
P
a
r
k
,
W
.
Le
e
,
a
n
d
K
.
Y
.
H
u
h
,
“
M
o
d
e
l
o
r
d
e
r
r
e
d
u
c
t
i
o
n
b
y
r
a
d
i
a
l
b
a
si
s
f
u
n
c
t
i
o
n
n
e
t
w
o
r
k
f
o
r
s
p
a
r
s
e
r
e
c
o
n
s
t
r
u
c
t
i
o
n
o
f
a
n
i
n
d
u
s
t
r
i
a
l
n
a
t
u
r
a
l
g
a
s
b
o
i
l
e
r
,
”
C
a
s
e
S
t
u
d
i
e
s i
n
T
h
e
rm
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
3
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
s
i
t
e
.
2
0
2
2
.
1
0
2
2
8
8
.
[
1
3
]
Z.
Li
u
,
Y
.
Z
h
a
n
g
,
S
.
Y
a
n
g
,
a
n
d
Y
.
L
y
u
,
“
M
u
l
t
i
v
a
r
i
a
t
e
c
o
o
p
e
r
a
t
i
v
e
i
n
t
e
r
n
a
l
mo
d
e
c
o
n
t
r
o
l
o
f
R
B
F
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
p
o
w
e
r
sy
st
e
m
c
h
a
o
s
su
p
p
r
e
ssi
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
3
9
1
1
2
–
1
3
9
1
2
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
4
0
8
6
1
.
[
1
4
]
Y
.
D
i
n
g
,
P
.
T
i
w
a
r
i
,
F
.
G
u
o
,
a
n
d
Q
.
Zo
u
,
“
S
h
a
r
e
d
su
b
s
p
a
c
e
-
b
a
se
d
r
a
d
i
a
l
b
a
s
i
s
f
u
n
c
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
i
d
e
n
t
i
f
y
i
n
g
n
c
R
N
A
s
su
b
c
e
l
l
u
l
a
r
l
o
c
a
l
i
z
a
t
i
o
n
,
”
N
e
u
ra
l
N
e
t
w
o
rks
,
v
o
l
.
1
5
6
,
p
p
.
1
7
0
–
1
7
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
2
2
.
0
9
.
0
2
6
.
[
1
5
]
A
.
K
a
p
n
o
p
o
u
l
o
s
,
C
.
K
a
z
a
k
i
d
i
s,
a
n
d
A
.
A
l
e
x
a
n
d
r
i
d
i
s
,
“
Q
u
a
d
r
o
t
o
r
t
r
a
j
e
c
t
o
r
y
t
r
a
c
k
i
n
g
b
a
s
e
d
o
n
b
a
c
k
s
t
e
p
p
i
n
g
c
o
n
t
r
o
l
a
n
d
r
a
d
i
a
l
b
a
s
i
s fu
n
c
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
Re
s
u
l
t
s
i
n
C
o
n
t
r
o
l
a
n
d
O
p
t
i
m
i
z
a
t
i
o
n
,
v
o
l
.
1
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
c
o
.
2
0
2
3
.
1
0
0
3
3
5
.
[
1
6
]
S
.
L
i
a
n
g
a
n
d
Y
.
Zh
a
n
g
,
“
I
n
t
e
l
l
i
g
e
n
t
a
t
t
i
t
u
d
e
f
a
u
l
t
-
t
o
l
e
r
a
n
t
c
o
n
t
r
o
l
o
f
s
p
a
c
e
t
u
m
b
l
i
n
g
t
a
r
g
e
t
f
l
y
-
a
r
o
u
n
d
b
a
s
e
d
o
n
R
B
F
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
6
6
1
0
–
6
6
2
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
3
.
3
2
3
7
5
6
5
.
[
1
7
]
S
.
T
u
,
K
.
B
e
n
,
L
.
T
i
a
n
,
a
n
d
L
.
Z
h
a
n
g
,
“
C
o
m
b
i
n
a
t
i
o
n
o
f
S
O
M
a
n
d
R
B
F
b
a
s
e
d
o
n
i
n
c
r
e
m
e
n
t
a
l
l
e
a
r
n
i
n
g
f
o
r
a
c
o
u
s
t
i
c
f
a
u
l
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
u
n
d
e
r
w
a
t
e
r
v
e
h
i
c
l
e
s
,
”
i
n
2
0
0
8
C
o
n
g
r
e
s
s
o
n
I
m
a
g
e
a
n
d
S
i
g
n
a
l
P
r
o
c
e
s
s
i
n
g
,
2
0
0
8
,
p
p
.
3
8
–
42
,
d
o
i
:
1
0
.
1
1
0
9
/
c
i
s
p
.
2
0
0
8
.
4
1
8
.
[
1
8
]
A
.
H
.
O
s
m
a
n
a
n
d
A
.
A
.
A
l
z
a
h
r
a
n
i
,
“
N
e
w
a
p
p
r
o
a
c
h
f
o
r
a
u
t
o
m
a
t
e
d
e
p
i
l
e
p
t
i
c
d
i
s
e
a
s
e
d
i
a
g
n
o
s
i
s
u
s
i
n
g
a
n
i
n
t
e
g
r
a
t
e
d
s
e
l
f
-
o
r
g
a
n
i
z
a
t
i
o
n
m
a
p
a
n
d
r
a
d
i
a
l
b
a
s
i
s
f
u
n
c
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
l
g
o
r
i
t
h
m
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
7
,
p
p
.
4
7
4
1
–
4
7
4
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
1
8
.
2
8
8
6
6
0
8
.
[
1
9
]
G.
-
B
.
H
u
a
n
g
,
Q
.
-
Y
.
Z
h
u
,
a
n
d
C
.
-
K
.
S
i
e
w
,
“
E
x
t
r
e
me
l
e
a
r
n
i
n
g
m
a
c
h
i
n
e
:
t
h
e
o
r
y
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
0
,
n
o
.
1
–
3
,
p
p
.
4
8
9
–
5
0
1
,
2
0
0
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
0
5
.
1
2
.
1
2
6
.
[
2
0
]
M
.
N
a
h
i
d
u
z
z
a
m
a
n
e
t
a
l
.
,
“
D
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
si
n
g
p
a
r
a
l
l
e
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
s
e
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
o
r
a
n
d
E
LM
c
l
a
ss
i
f
i
e
r
,
”
E
x
p
e
rt
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
1
9
5
5
7
.
[
2
1
]
M
.
O
.
F
.
G
o
n
i
e
t
a
l
.
,
“
F
a
st
a
n
d
a
c
c
u
r
a
t
e
f
a
u
l
t
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
t
r
a
n
smis
si
o
n
l
i
n
e
s
u
si
n
g
e
x
t
r
e
me
l
e
a
r
n
i
n
g
mac
h
i
n
e
,
”
e
-
Pri
m
e
-
A
d
v
a
n
c
e
s
i
n
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
E
n
e
r
g
y
,
v
o
l
.
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
i
me
.
2
0
2
3
.
1
0
0
1
0
7
.
[
2
2
]
M
.
N
a
h
i
d
u
z
z
a
ma
n
e
t
a
l
.
,
“
A
n
o
v
e
l
met
h
o
d
f
o
r
m
u
l
t
i
v
a
r
i
a
n
t
p
n
e
u
m
o
n
i
a
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
h
y
b
r
i
d
C
N
N
-
P
C
A
b
a
se
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
u
si
n
g
e
x
t
r
e
m
e
l
e
a
r
n
i
n
g
ma
c
h
i
n
e
w
i
t
h
C
X
R
i
ma
g
e
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
4
7
5
1
2
–
1
4
7
5
2
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
2
3
7
8
2
.
[
2
3
]
S
.
N
.
S
i
v
a
n
a
n
d
a
m,
S
.
S
u
m
a
t
h
i
,
a
n
d
S
.
N
.
D
e
e
p
a
,
I
n
t
r
o
d
u
c
t
i
o
n
t
o
n
e
u
r
a
l
n
e
t
w
o
rks
u
si
n
g
M
ATL
AB
6
.
0
.
N
e
w
D
e
l
h
i
,
I
n
d
i
a
:
T
a
t
a
M
c
G
r
a
w
-
H
i
l
l
P
u
b
l
i
sh
i
n
g
,
2
0
0
6
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
5
4
0
-
3
5
7
8
1
-
0.
[
2
4
]
G
.
W
a
n
g
a
n
d
Z.
S
.
D
.
S
o
o
,
“
B
E
-
EL
M
:
b
i
o
l
o
g
i
c
a
l
e
n
se
mb
l
e
e
x
t
r
e
me
l
e
a
r
n
i
n
g
m
a
c
h
i
n
e
w
i
t
h
o
u
t
t
h
e
n
e
e
d
o
f
e
x
p
l
i
c
i
t
a
g
g
r
e
g
a
t
i
o
n
,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
0
6
7
7
.
[
2
5
]
Y
.
Z
h
a
n
g
e
t
a
l
.
,
“
S
p
e
c
t
r
o
s
c
o
p
i
c
p
r
o
f
i
l
i
n
g
-
b
a
s
e
d
g
e
o
g
r
a
p
h
i
c
h
e
r
b
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
y
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
r
a
n
d
o
m
w
e
i
g
h
t
s,
”
S
p
e
c
t
ro
c
h
i
m
i
c
a
Ac
t
a
P
a
rt
A:
M
o
l
e
c
u
l
a
r
a
n
d
Bi
o
m
o
l
e
c
u
l
a
r
S
p
e
c
t
r
o
s
c
o
p
y
,
v
o
l
.
2
7
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sa
a
.
2
0
2
2
.
1
2
1
3
4
8
.
[
2
6
]
R
.
d
e
A
l
m
e
i
d
a
,
Y
.
M
.
G
o
h
,
R
.
M
o
n
f
a
r
e
d
,
M
.
T
.
A
.
S
t
e
i
n
e
r
,
a
n
d
A
.
W
e
s
t
,
“
A
n
e
n
s
e
m
b
l
e
b
a
s
e
d
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s
w
i
t
h
r
a
n
d
o
m
w
e
i
g
h
t
s
f
o
r
o
n
l
i
n
e
d
a
t
a
s
t
r
e
a
m
r
e
g
r
e
s
s
i
o
n
,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
4
,
n
o
.
1
3
,
p
p
.
9
8
3
5
–
9
8
5
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
0
1
9
-
0
4
4
9
9
-
x.
[
2
7
]
R
.
G
u
a
t
e
l
l
i
,
V
.
A
u
b
i
n
,
M
.
M
o
r
a
,
J.
N
.
-
To
r
r
e
s,
a
n
d
A
.
M
.
-
O
l
i
v
a
r
i
,
“
D
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
so
n
’
s
d
i
se
a
se
b
a
s
e
d
o
n
sp
e
c
t
r
o
g
r
a
m
s
o
f
v
o
i
c
e
r
e
c
o
r
d
i
n
g
s
a
n
d
e
x
t
r
e
me
l
e
a
r
n
i
n
g
ma
c
h
i
n
e
r
a
n
d
o
m
w
e
i
g
h
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
E
n
g
i
n
e
e
ri
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
2
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
3
.
1
0
6
7
0
0
.
[
2
8
]
Y
.
Zh
a
n
g
,
J.
C
a
o
,
B
.
Z
h
a
n
g
,
X
.
Z
h
e
n
g
,
a
n
d
W
.
C
h
e
n
,
“
A
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
d
i
f
f
e
r
e
n
t
r
a
d
i
a
l
b
a
si
s
f
u
n
c
t
i
o
n
i
n
t
e
r
p
o
l
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
i
n
t
h
e
r
e
c
o
n
s
t
r
u
c
t
i
o
n
a
n
d
p
a
t
h
p
l
a
n
n
i
n
g
o
f
γ
r
a
d
i
a
t
i
o
n
f
i
e
l
d
s
,
”
N
u
c
l
e
a
r
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
5
6
,
n
o
.
7
,
p
p
.
2
8
0
6
–
2
8
2
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
t
.
2
0
2
4
.
0
2
.
0
4
3
.
[
2
9
]
A
.
F
a
r
i
a
s,
N
.
W
.
P
a
s
c
h
o
a
l
i
n
o
t
o
,
E.
C
.
B
o
r
d
i
n
a
ssi
,
F
.
L
e
o
n
a
r
d
i
,
a
n
d
S
.
D
e
l
i
j
a
i
c
o
v
,
“
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
l
i
n
g
o
f
r
e
si
d
u
a
l
s
t
r
e
ss
i
n
t
u
r
n
i
n
g
o
f
h
a
r
d
m
a
t
e
r
i
a
l
s
u
s
i
n
g
r
a
d
i
a
l
b
a
si
s
f
u
n
c
t
i
o
n
n
e
t
w
o
r
k
e
n
h
a
n
c
e
d
w
i
t
h
p
r
i
n
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
l
y
si
s,”
E
n
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
a
n
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
,
v
o
l
.
5
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
s
t
c
h
.
2
0
2
4
.
1
0
1
7
4
3
.
[
3
0
]
A
.
N
.
V
a
n
t
y
g
h
e
m
e
t
a
l
.
,
“
R
o
t
a
t
i
o
n
a
n
d
f
l
i
p
p
i
n
g
i
n
v
a
r
i
a
n
t
s
e
l
f
-
o
r
g
a
n
i
z
i
n
g
m
a
p
s
w
i
t
h
a
s
t
r
o
n
o
m
i
c
a
l
i
m
a
g
e
s
:
a
c
o
o
k
b
o
o
k
a
n
d
a
p
p
l
i
c
a
t
i
o
n
t
o
t
h
e
V
L
A
s
k
y
s
u
r
v
e
y
Q
u
i
c
k
L
o
o
k
i
m
a
g
e
s
,
”
A
s
t
r
o
n
o
m
y
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
4
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
c
o
m
.
2
0
2
4
.
1
0
0
8
2
4
.
[
3
1
]
V
.
R
.
C
a
r
r
e
i
r
a
,
R
.
B
i
j
a
n
i
,
a
n
d
C
.
F
.
P
.
-
N
e
t
o
,
“
R
e
c
o
n
s
t
r
u
c
t
i
o
n
o
f
l
i
t
h
o
f
a
c
i
e
s
u
s
i
n
g
a
s
u
p
e
r
v
i
s
e
d
s
e
l
f
-
o
r
g
a
n
i
z
i
n
g
m
a
p
:
a
p
p
l
i
c
a
t
i
o
n
i
n
p
s
e
u
d
o
-
w
e
l
l
s
b
a
s
e
d
o
n
a
s
y
n
t
h
e
t
i
c
g
e
o
l
o
g
i
c
c
r
o
s
s
-
s
e
c
t
i
o
n
,
”
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
G
e
o
s
c
i
e
n
c
e
s
,
v
o
l
.
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
g
.
2
0
2
4
.
1
0
0
0
7
2
.
[
3
2
]
P
.
A
n
a
n
d
,
A
.
B
h
a
r
t
i
,
a
n
d
R
.
R
a
s
t
o
g
i
,
“
T
i
me
e
f
f
i
c
i
e
n
t
v
a
r
i
a
n
t
s
o
f
t
w
i
n
e
x
t
r
e
me
l
e
a
r
n
i
n
g
ma
c
h
i
n
e
,
”
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sw
a
.
2
0
2
2
.
2
0
0
1
6
9
.
[
3
3
]
A
.
D
h
i
n
i
,
I
.
S
u
r
j
a
n
d
a
r
i
,
B
.
K
u
su
m
o
p
u
t
r
o
,
a
n
d
A
.
K
u
s
i
a
k
,
“
E
x
t
r
e
me
l
e
a
r
n
i
n
g
mac
h
i
n
e
–
r
a
d
i
a
l
b
a
s
i
s
f
u
n
c
t
i
o
n
(
E
L
M
-
R
B
F
)
n
e
t
w
o
r
k
s
f
o
r
d
i
a
g
n
o
si
n
g
f
a
u
l
t
s
i
n
a
st
e
a
m
t
u
r
b
i
n
e
,
”
J
o
u
r
n
a
l
o
f
I
n
d
u
st
r
i
a
l
a
n
d
Pr
o
d
u
c
t
i
o
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
9
,
n
o
.
7
,
p
p
.
5
7
2
–
5
8
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
0
/
2
1
6
8
1
0
1
5
.
2
0
2
1
.
1
8
8
7
9
4
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
322
-
3
2
8
328
[
3
4
]
G
.
K
i
m
a
n
d
B
.
C
.
K
i
m,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
f
u
n
c
t
i
o
n
a
l
t
y
p
e
s
o
f
l
i
n
e
s
i
n
P
&I
D
s
u
s
i
n
g
a
g
r
a
p
h
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
7
3
6
8
0
–
7
3
6
8
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
6
2
2
3
.
[
3
5
]
S
.
K
.
G
o
w
d
a
,
S
.
N
.
M
u
r
t
h
y
,
J.
S
.
H
i
r
e
mat
h
,
S
.
L.
B
.
S
u
b
r
a
ma
n
y
a
,
S
.
S
.
H
i
r
e
ma
t
h
,
a
n
d
M
.
S
.
H
i
r
e
ma
t
h
,
“
A
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
b
a
s
e
d
o
n
s
p
a
t
i
o
-
t
e
mp
o
r
a
l
f
e
a
t
u
r
e
s
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
I
AE
S
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
2
1
0
2
–
2
1
1
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
2
.
p
p
2
1
0
2
-
2
1
1
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dw
i
Ma
r
isa
M
id
y
a
n
ti
is
a
lec
tu
re
r
in
C
o
m
p
u
ter
En
g
i
n
e
e
rin
g
t
h
e
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s,
Un
iv
e
rsitas
Tan
ju
n
g
p
u
ra
,
si
n
c
e
2
0
1
5
.
S
h
e
g
o
t
h
e
r
M
.
Cs.
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
lec
tro
n
ics
fr
o
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
in
2
0
1
3
.
He
r
re
se
a
rc
h
i
n
tere
sts
in
c
l
u
d
e
n
e
u
ra
l
n
e
t
wo
rk
s
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
f
u
z
z
y
lo
g
ic.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
wi.
m
a
risa
@s
isk
o
m
.
u
n
tan
.
a
c
.
id
.
S
y
a
m
sul
Ba
h
r
i
is
c
u
rre
n
tl
y
a
l
e
c
tu
re
r
a
t
th
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s,
Un
i
v
e
rsitas
Tan
j
u
n
g
p
u
ra
,
si
n
c
e
2
0
1
5
.
He
g
o
t
h
is
M
.
Cs.
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
El
e
c
tro
n
ics
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
i
n
2
0
1
4
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
i
n
t
e
ll
ig
e
n
c
e
,
d
a
ta
m
i
n
in
g
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
sy
a
m
su
l.
b
a
h
ri@sis
k
o
m
.
u
n
tan
.
a
c
.
id
.
Ilh
a
m
s
y
a
h
o
b
tai
n
e
d
a
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
d
e
g
re
e
fro
m
t
h
e
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s,
Tan
ju
n
g
p
u
ra
Un
i
v
e
rsity
in
2
0
0
7
.
His
m
a
ste
r
in
C
o
m
p
u
ter
S
c
ien
c
e
d
e
g
re
e
wa
s
o
b
tai
n
e
d
fr
o
m
t
h
e
U
n
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
in
2
0
1
0
.
H
e
is
a
l
e
c
tu
re
r
a
t
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
o
n
S
y
ste
m
,
Tan
ju
n
g
p
u
ra
Un
i
v
e
rsity
,
In
d
o
n
e
sia
.
Hi
s
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
re
c
o
m
m
e
n
d
a
ti
o
n
s
y
ste
m
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
il
h
a
m
sy
a
h
@s
isfo
.
u
n
ta
n
.
a
c
.
id
.
Za
li
k
h
a
h
K
h
a
iru
n
n
isa
i
s
a
stu
d
e
n
t
m
a
jo
rin
g
in
In
f
o
r
m
a
ti
c
s,
F
a
c
u
lt
y
o
f
En
g
i
n
e
e
rin
g
,
Tan
j
u
n
g
p
u
ra
Un
i
v
e
rsity
,
wh
o
is
c
u
rre
n
tl
y
in
h
e
r
first
y
e
a
r
o
f
e
d
u
c
a
ti
o
n
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta
sc
ien
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
1
0
4
1
2
4
1
0
1
8
@s
t
u
d
e
n
t.
u
n
tan
.
a
c
.
id
.
H
a
fizha
h
I
n
sa
n
i
Mi
d
y
a
n
ti
is
a
l
e
c
tu
re
r
in
th
e
M
u
sic
S
tu
d
y
P
r
o
g
ra
m
,
F
a
c
u
l
ty
o
f
Art
a
n
d
De
sig
n
Ed
u
c
a
ti
o
n
,
U
n
i
v
e
rsitas
P
e
n
d
id
i
k
a
n
I
n
d
o
n
e
sia
w
it
h
a
c
o
n
c
e
n
trati
o
n
in
d
ig
it
a
l
m
u
sic
,
c
o
m
p
u
ter
m
u
sic
,
a
n
d
p
i
a
n
o
.
S
h
e
e
n
tere
d
t
h
e
u
n
d
e
rg
ra
d
u
a
te
e
d
u
c
a
ti
o
n
le
v
e
l
a
t
t
h
e
Un
iv
e
rsitas
P
e
n
d
i
d
ik
a
n
I
n
d
o
n
e
si
a
,
m
a
jo
rin
g
in
c
o
m
p
u
ter
sc
ien
c
e
,
a
n
d
m
a
ste
r'
s
a
t
th
e
g
ra
d
u
a
te
sc
h
o
o
l
o
f
t
h
e
Un
i
v
e
rsitas
P
e
n
d
i
d
ik
a
n
I
n
d
o
n
e
sia
with
a
c
o
n
c
e
n
trat
io
n
in
m
u
sic
a
rts
e
d
u
c
a
ti
o
n
.
He
r
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
t
h
e
field
o
f
a
rt
ifi
c
ial
i
n
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
s,
d
ig
it
a
l
si
g
n
a
l
p
ro
c
e
ss
in
g
,
d
i
g
it
a
l
m
u
sic
,
d
a
n
m
u
sic
c
o
m
p
u
ter.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
ice
m
id
y
a
n
ti
@
u
p
i
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.